Sphere Generative Adversarial Network Based on Geometric Moment Matching

By Sung Woo Park, Junseok Kwon. 2019

33 citations recorded by the source corpus.

We propose sphere generative adversarial network (GAN), a novel integral probability metric (IPM)-based GAN. Sphere GAN uses the hypersphere to bound IPMs in the objective function. Thus, it can be trained stably. On the hypersphere, sphere GAN exploits the information of higher-order statistics of data using geometric moment matching, thereby providing more accurate results. In the paper, we mathematically prove the good properties of sphere GAN. In experiments, sphere GAN quantitatively and qualitatively surpasses recent state-of-the-art GANs for unsupervised image generation problems with the CIFAR-10, STL-10, and LSUN bedroom datasets. Source code is available at https://github.com/pswkiki/SphereGAN.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Weiyang Liu
2. Adrian Weller
3. Zhen Liu
4. Rongmei Lin
5. Bhiksha Raj
6. Rita Singh
7. Yandong Wen
8. Li Xiong

Citations in the corpus

• Generative Adversarial Networks (2021, neutral): “As summarized in Table II, there are many exciting future directions for GANs, including improving the scalability and stability of GANs, developing more advanced architectures, incorporating domain knowledge, exploring new applications of GANs, and developing more robust evaluation metrics.”
• Learning with Hyperspherical Uniformity (2021, background): “[51, 52, 49, 48, 50, 80, 79, 20, 19, 60, 14, 47] propose to learn representations on hypersphere and show that angular information in neural networks, in contrast to magnitude, preserves the key semantics and is very crucial to generalization.”
• SphereFace Revived: Unifying Hyperspherical Face Recognition (2021, background): “Beyond face recognition, the idea of learning a representation on the hypersphere is also shown generally useful in a diverse set of applications, such as few-shot recognition [47], [48], [49], [50], [51], deep metric learning [25], [52], self-supervised learning [53], [54], [55], [56], generative m”